Punchwes's repositories
AGGCN
Attention Guided Graph Convolutional Networks for Relation Extraction (authors' PyTorch implementation for the ACL19 paper)
awesome-sentence-embedding
A curated list of pretrained sentence and word embedding models
bpemb
Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
ccks2019
实体识别比赛
CompGCN
ICLR 2020: Composition-Based Multi-Relational Graph Convolutional Networks
context-probes
Using syntactic and semantic probing tasks to evaluate how contextual word embeddings encode language
DiscoBERT
Code for paper "Discourse-Aware Neural Extractive Text Summarization" (ACL20)
EvalRank-Embedding-Evaluation
ACL 2022: Just Rank: Rethinking Evaluation with Word and Sentence Similarities
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
GNNs-for-NLP
Graph Neural Networks for Natural Language Processing tutorial at EMNLP 2019 and CODS-COMAD 2020
NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
nlp-text-mining-working-examples
Full working examples with accompanying dataset for Text Mining and NLP. Current code base: Gensim Word2Vec, Phrase Embeddings, Keyword Extraction with TF-IDF and SKlearn, Word Count with PySpark
numpy-ml
Machine learning, in numpy
paraphrase-metrics
ACL 2022 paper "Towards Better Characterization of Paraphrases"
Representations_Of_Syntax
Code and Resources for the paper 'Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs' by Lepori, Linzen, and McCoy
SATA-Tree-LSTM
Implementation of SATA Tree-LSTM (Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations, AAAI 2019)
SCAN
Simple language-driven navigation tasks for studying compositional learning
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
SentEval
A python tool for evaluating the quality of sentence embeddings.
serve
Model Serving on PyTorch
stanza
Official Stanford NLP Python Library for Many Human Languages
tag-classification-framework
Framework for building pipelines of NLP processing and classification
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
WikipediaSample
A sample of 10,000 wikipedia articles for use as an SPD background corpus
WordGCN
ACL 2019: Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks